© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6347
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and their actions, particularly in contexts of conflict or decision-making

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.06
    3:0.27
    4:0.02
    5:0.07
    6:0.02
    7:0.04
    8:0.04
    9:0.01
    10:0.33
    11:0.02
    Negative Logits
    anski
    -2.37
    oller
    -2.14
    anson
    -2.11
    Recommend
    -2.05
    ]."
    -1.97
     Detention
    -1.96
     ASAP
    -1.87
    umblr
    -1.86
    "]=>
    -1.84
     guiName
    -1.84
    POSITIVE LOGITS
     infall
    2.23
     merely
    2.18
    Were
    2.10
    ��
    2.07
     belonged
    2.04
     accomplishment
    2.01
    ties
    1.93
     oneself
    1.93
     invented
    1.92
     gods
    1.90
    Activations Density 0.044%

    No Known Activations